Out-of-Distribution (OOD) detection is a cornerstone for the safe deployment of AI systems in the open world. However, existing methods treat OOD detection as a binary classification problem, a cognitive flattening that fails to distinguish between semantically close (Near-OOD) and distant (Far-OOD) unknown risks. This limitation poses a significant safety bottleneck in applications requiring fine-grained risk stratification. To address this, we propose a paradigm shift from a conventional probabilistic view to a principled information-theoretic framework. We formalize the core task as quantifying the Semantic Surprise of a new sample and introduce a novel ternary classification challenge: In-Distribution (ID) vs. Near-OOD vs. Far-OOD. The theoretical foundation of our work is the concept of Low-Entropy Semantic Manifolds, which are explicitly structured to reflect the data's intrinsic semantic hierarchy. To construct these manifolds, we design a Hierarchical Prototypical Network. We then introduce the Semantic Surprise Vector (SSV), a universal probe that decomposes a sample's total surprise into three complementary and interpretable dimensions: conformity, novelty, and ambiguity. To evaluate performance on this new task, we propose the Normalized Semantic Risk (nSR), a cost-sensitive metric. Experiments demonstrate that our framework not only establishes a new state-of-the-art (sota) on the challenging ternary task, but its robust representations also achieve top results on conventional binary benchmarks, reducing the False Positive Rate by over 60% on datasets like LSUN.

翻译：分布外（OOD）检测是人工智能系统在开放世界中安全部署的基石。然而，现有方法将OOD检测视为一个二元分类问题，这种认知扁平化无法区分语义相近（近OOD）与语义遥远（远OOD）的未知风险。这一局限在需要细粒度风险分层的应用中构成了显著的安全瓶颈。为解决此问题，我们提出了一种从传统概率视角转向原则性信息论框架的范式转变。我们将核心任务形式化为量化新样本的语义惊奇，并引入一种新颖的三元分类挑战：分布内（ID）vs. 近OOD vs. 远OOD。我们工作的理论基础是低熵语义流形的概念，该流形经过显式结构化以反映数据的内在语义层次。为构建这些流形，我们设计了一个分层原型网络。随后，我们引入了语义惊奇向量（SSV），这是一种通用探针，可将样本的总惊奇分解为三个互补且可解释的维度：一致性、新颖性和模糊性。为评估这一新任务的性能，我们提出了归一化语义风险（nSR），一种成本敏感度量指标。实验表明，我们的框架不仅在具有挑战性的三元任务上建立了新的最先进水平（sota），其鲁棒表示还在传统二元基准测试中取得了顶尖结果，在LSUN等数据集上将误报率降低了超过60%。